Python爬虫入门级

Python爬虫入门级 Python爬虫入门级（九）

Xpath实战 ：猪八戒网

重点： 点击页面——》右键检查——》点击代码右键——》copy xpath！！！！

#In[]
####Xpath实战 ：猪八戒网

## 1、拿到页面源代码
## 2、提取和解析数据
import requests
from lxml import etree

url = "https://beijing.zbj.com/search/f/?type=new&kw=saas"
resp = requests.get(url)
# print(resp.text)
#解析
html  = etree.HTML(resp.text)

#拿到每一个服务商的div
divs = html.xpath("/html/body/div[6]/div/div/div[2]/div[5]/div[1]/div")
for div in divs:
    price = div.xpath("./div/div/a[2]/div[2]/div[1]/span[1]/text()")[0].strip("¥")
    businiss = div.xpath("./div/div/a[1]/div[1]/p/text()")[1].strip('n')
    title = "saas" + div.xpath("./div/div/a[2]/div[2]/div[2]/p/text()")[0]
    num = div.xpath("./div/div/a[2]/div[2]/div[1]/span[2]/text()")[0]
    location = div.xpath("./div/div/a[1]/div[1]/div/span/text()")[0]
    if div.xpath("./div/div/a[1]/div[2]/span[2]/i[2]/text()") == [] or div.xpath("./div/div/a[1]/div[2]/span[2]/i[2]/text()") == '' or div.xpath("./div/div/a[1]/div[2]/span[2]/i[2]/text()") is None:
        location_issue = "NULL"
    else:   
        star_level = div.xpath("./div/div/a[1]/div[2]/span[2]/i[2]/text()")[0]
    if div.xpath("./div/div/a[1]/div[2]/span[3]/i/text()") == [] or div.xpath("./div/div/a[1]/div[2]/span[3]/i/text()") == '' or div.xpath("./div/div/a[1]/div[2]/span[3]/i/text()") is None:
        location_issue = "NULL"
    else:    
        location_issue = div.xpath("./div/div/a[1]/div[2]/span[3]/i/text()")[0]
        # print(location_issue)

    print(location + 't' + star_level + 't' + location_issue + 't' + businiss + 't' + title + 't' + price + 't' + num)

    # print(div.xpath("./div/div/a[1]/div[2]/span[3]/i/text()"))